Every CVE Search/ Get API key

CVE-2026-33234

AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server

5.0 MediumPublic exploit

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
Low
User interaction
None

What an attacker can affect

Confidentiality
Low
Integrity
None
Availability
None

Exploit likelihood

0.30%Up 0.3 points since May 19, 2026
90%50%10%1%

What each source reports

CVE List Score used 5.0

AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.

Record
CVE-2026-33234
CVSS 3.1
5.0 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
Weakness
CWE-918
Updated
2026-11-02
EUVDEUVD-2026-30822 5.0

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.

Record
EUVD-2026-30822
CVSS 3.1
5.0 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
Updated
2026-11-02
NVD 5.0

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.

Record
CVE-2026-33234
CVSS 3.1
5.0 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
Weakness
CWE-918
Updated
2026-11-02
OSV 5.0

AutoGPT: SendEmailBlock's IP blocklist bypass allows SSRF via user-controlled SMTP server

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51, SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52.

Record
CVE-2026-33234
CVSS 3.1
5.0 MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N
Weakness
CWE-918
Updated
2026-11-02

Affected products

Public exploits

Links only. Every CVE stores no exploit code.

Public exploits
SourceLinkDate
PoC in GitHubpavanchow/CVE-2026-332342026-09-07

History

History
RecordedChangedSources
first indexedCVE List, EUVD, NVD, OSV, PoC in GitHub

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-33234 is a medium vulnerability (CVSS 5.0) in Significant-gravitas Autogpt, published May 19, 2026. Public exploit code exists. EPSS puts the chance of exploitation in the next 30 days at 0.30%, the 23rd percentile. No source names a fixed version.

References

MoveEnter Open